Provides durable one-by-one review workflows for coding agents handling multi-item work. Items flow through lifecycle states (pending, in-progress, deferred, blocked, completed, skipped) with priority scoring that automatically recalculates ordering. Supports nested child sessions that pause parent workflows, blocked-item tracking with metadata, and first-class approval updates independent of lifecycle state. Session state persists as JSON files enabling deterministic recovery across agent restarts.
Cognium trust score
50%
Tier
Unverified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.